Measurement Guidance in Diffusion Models: Insight from Medical Image Synthesis

计算机科学 人工智能 计算机视觉 医学影像学 图像处理 扩散 图像(数学) 模式识别(心理学) 物理 热力学
作者
Yimin Luo,Qinyu Yang,Yuheng Fan,Haikun Qi,Menghan Xia
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:46 (12): 7983-7997 被引量:1
标识
DOI:10.1109/tpami.2024.3399098
摘要

In the field of healthcare, the acquisition of sample is usually restricted by multiple considerations, including cost, labor- intensive annotation, privacy concerns, and radiation hazards, therefore, synthesizing images-of-interest is an important tool to data augmentation. Diffusion models have recently attained state-of-the-art results in various synthesis tasks, and embedding energy functions has been proved that can effectively guide the pre-trained model to synthesize target samples. However, we notice that current method development and validation are still limited to improving indicators, such as Fréchet Inception Distance score (FID) and Inception Score (IS), and have not provided deeper investigations on downstream tasks, like disease grading and diagnosis. Moreover, existing classifier guidance which can be regarded as a special case of energy function can only has a singular effect on altering the distribution of the synthetic dataset. This may contribute to in-distribution synthetic sample that has limited help to downstream model optimization. All these limitations remind that we still have a long way to go to achieve controllable generation. In this work, we first conducted an analysis on previous guidance as well as its contributions on further applications from the perspective of data distribution. To synthesize samples which can help downstream applications, we then introduce uncertainty guidance in each sampling step and design an uncertainty-guided diffusion models. Extensive experiments on four medical datasets, with ten classic networks trained on the augmented sample sets provided a comprehensive evaluation on the practical contributions of our methodology. Furthermore, we provide a theoretical guarantee for general gradient guidance in diffusion models, which would benefit future research on investigating other forms of measurement guidance for specific generative tasks. Codes and models are available at: https://github.com/yangqy1110/MGDM
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
大模型应助焓晓芈采纳,获得10
刚刚
xyzdmmm完成签到,获得积分10
刚刚
Haibara5发布了新的文献求助10
1秒前
1秒前
凤迎雪飘完成签到,获得积分10
2秒前
叶子完成签到,获得积分10
2秒前
平淡的初翠完成签到 ,获得积分10
2秒前
甜甜穆完成签到,获得积分10
2秒前
豪的花花完成签到,获得积分10
4秒前
帅气的亦绿完成签到,获得积分10
4秒前
koutianle完成签到 ,获得积分10
5秒前
yan完成签到,获得积分10
6秒前
非对称转录完成签到,获得积分0
6秒前
SYSUer发布了新的文献求助10
6秒前
6秒前
plumcute完成签到,获得积分10
7秒前
wure10完成签到 ,获得积分10
7秒前
生活不是电影完成签到,获得积分10
8秒前
想人陪的飞薇完成签到 ,获得积分10
9秒前
七七发布了新的文献求助10
11秒前
爱听歌凤灵完成签到,获得积分10
12秒前
12秒前
所所应助坚强的安柏采纳,获得10
12秒前
panfan完成签到,获得积分10
12秒前
12秒前
Abi完成签到,获得积分10
13秒前
DijiaXu完成签到,获得积分10
13秒前
清脆的靖仇应助1111采纳,获得10
14秒前
忐忑的邑完成签到,获得积分10
14秒前
鳄鱼蛋完成签到,获得积分10
14秒前
ENG完成签到,获得积分10
15秒前
仝富贵完成签到,获得积分10
16秒前
16秒前
认真的灵竹完成签到 ,获得积分10
16秒前
dahuihui发布了新的文献求助10
17秒前
xx完成签到,获得积分10
17秒前
犹豫的天问完成签到,获得积分10
17秒前
木木三发布了新的文献求助10
17秒前
18秒前
lzl008完成签到 ,获得积分10
18秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968593
求助须知:如何正确求助?哪些是违规求助? 3513416
关于积分的说明 11167791
捐赠科研通 3248853
什么是DOI,文献DOI怎么找? 1794507
邀请新用户注册赠送积分活动 875170
科研通“疑难数据库(出版商)”最低求助积分说明 804671